# QueryGym: Step-by-Step Interaction with Relational Databases

arXiv: https://arxiv.org/abs/2509.21674 · HTML: https://mlsanity.com/paper/2509.21674/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [SParC: Cross-Domain Semantic Parsing in Context](https://mlsanity.com/paper/1906.02285/) (2019)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries](https://mlsanity.com/paper/2010.11246/) (2020)
- [Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL](https://mlsanity.com/paper/2504.15077/) (2025)
- [RAISE: Reasoning Agent for Interactive SQL Exploration](https://mlsanity.com/paper/2506.01273/) (2025)

## Built on by (most cited first, 1 of 1)

- [Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL](https://mlsanity.com/paper/2609.33670/) (2026)

## Abstract (arXiv)

We introduce QueryGym, an interactive environment for building, testing, and evaluating LLM-based query planning agents. Existing frameworks often tie agents to specific query language dialects or obscure their reasoning; QueryGym instead requires agents to construct explicit sequences of relational algebra operations, ensuring engine-agnostic evaluation and transparent step-by-step planning. The environment is implemented as a Gymnasium interface that supplies observations -- including schema details, intermediate results, and execution feedback -- and receives actions that represent database exploration (e.g., previewing tables, sampling column values, retrieving unique values) as well as relational algebra operations (e.g., filter, project, join). We detail the motivation and the design of the environment. In the demo, we showcase the utility of the environment by contrasting it with contemporary LLMs that query databases. QueryGym serves as a practical testbed for research in error remediation, transparency, and reinforcement learning for query generation. For the associated demo, see https://ibm.biz/QueryGym.